One deterministic model of every study.

SironaLex is a curated knowledge graph built for radiology — anatomic concepts, clinical conditions, modalities, protocols, and the relationships between them — released under version control. Every study is classified against it by a deterministic, explainable pipeline, which is what gives the platform one consistent understanding of a study regardless of how the source system named it.

Ontology coverage is curated and released under version control, so classification behavior is explainable and reviewable rather than drifting silently. When a release changes how a study is classified, you can see what changed and why.

A unified data model requires unified infrastructure from the ground up. Legacy systems fragment data across on-prem PACS, separate RIS, disconnected dictation, and third-party AI. Retrofitting semantic classification onto that is cosmetic, not architectural. Sirona was built cloud-native with unified data as the design principle in 2018 — a foundational choice that is hard to retrofit.

Instead of a protocol per series description, you build one protocol per semantic study type — 'all chest CTs with standard inspiration protocol and multi-planar reconstruction'. The system applies it to every matching study regardless of how it was labeled at ingest. Hundreds of variations collapse to a handful, and protocols travel cleanly across practices.

When AI is trained on studies unified by SironaLex, it learns from one consistent label for each kind of study rather than fifty local variants. That is what lets a model generalize across practices on the platform instead of being retrained on each practice's labels.

The Dashboard queries the unified semantic model directly — not fragmented PACS, RIS, and AI systems — so volume and turnaround can be broken down by semantic study type rather than by each site's labels.